Provided is a process including: obtaining, with one or more processors, a set of data comprising a plurality of patient records, selecting a subset of the plurality of parameters for inputs into a machine learning system, generating a classifier using the machine learning system based on the training data and the subset of the plurality of parameters for inputs; receiving, with one or more processors, patient record of a first user; performing an analysis, with one or more processors, to identify acoustic measures from a voice sample of the first user.

A method for partitioning of input vectors for coding is presented. The method comprises obtaining of an input vector. The input vector is segmented, in a non-recursive manner, into an integer number, N.sup.SEG, of input vector segments. A representation of a respective relative energy difference between parts of the input vector on each side of each boundary between the input vector segments is determined, in a recursive manner. The input vector segments and the representations of the relative energy differences are provided for individual coding. Partitioning units and computer programs for partitioning of input vectors for coding, as well as positional encoders, are presented.

The technology in this application compresses multi-antenna, complex-valued signals by exploiting both a spatial and a temporal correlation of the signals to remove redundancy within the complex-valued signals and substantially reduce the capacity requirement of backhaul links. At a receiver, the compressed signal is received, and a decompressor decompresses the received signal over space and over time to reconstruct the multiple antenna stream.

A method for pyramid vector quantization indexing of audio/video signals comprises obtaining of an integer input vector representing the audio/video signal samples. A leading sign is extracted from the integer input vector. The leading sign is a sign of a terminal non-zero coefficient in the integer input vector. The terminal non-zero coefficient is one of a first non-zero coefficient and a last non-zero coefficient in the integer input vector. The integer input vector is indexed with a pyramid vector quantization enumeration scheme into an output index representing the audio/video signal samples. The pyramid vector quantization enumeration scheme is designed for neglecting the sign of the terminal non-zero coefficient. The output index and the leading sign are outputted. A corresponding method for de-indexing, an encoder, a decoder, and computer programs therefore are also disclosed.

A computing device (100), comprising a memory (240) and a controller (210), wherein said controller (210) is configured to compress a file (410) by transforming at least a portion of said file (410) to a number (X) and transforming the number (X) to an exponent vector (exp) comprising at least one exponent, wherein each exponent corresponds to a base in a base vector (base).

There is a method of compressing image data comprising a set of image values each representing a position in image-value space so as to define an occupied region thereof. The method comprises selectively applying a series of compression transforms to subsets of the image data items to generate a transformed set of image data items occupying a compacted region of value space. The method further comprises identifying a set of one or more reference data items that quantizes the compacted region in value space. For each image data item in the set of image data items, a sequence of decompression transforms from a fixed set of decompression transforms is identified that generates an approximation of that image data item when applied to a selected one of the one or more reference data items. Each image data item in the set of image data items is encoded as a representation of the identified sequence of decompression transforms for that image data item. The encoded image data items, set of reference data items and the fixed set of decompression transforms are stored as compressed image data.

The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).

One embodiments is a computer-implemented method for finding a CUR decomposition. The method includes constructing, by a computer processor, a matrix C based on a matrix A. A matrix R is constructed based on the matrix A and the matrix C. A matrix U is constructed based on the matrices A, C, and R. The matrices C, U, and R provide a CUR decomposition of the matrix A. The construction of the matrices C, U, and R provide at least one of an input-sparsity-time CUR and a deterministic CUR.

Methods are provided for efficiently encoding and decoding multivariate correlated data sequences for transmission over multiple channels of a network. The methods include transforming data vectors from correlated sources into vectors that comprise substantially independent and correlated components, and generating a common information vector based on the correlated components, and two private information vectors. The methods also include computing the amount of information, such as Wyner's lossy common information, in the common information vector, computing rates that lie on the Gray-Wyner rate region, and choosing compression rates based on the amount of common information. The methods may be applicable, in general, to a wide range of communications and/or storage systems and, particularly, to sensor networks and multi-user virtual environments for gaming and other applications.

Techniques and systems are provided for implementing a convolutional neural network. One or more convolution accelerators are provided that each include a feature line buffer memory, a kernel buffer memory, and a plurality of multiply-accumulate (MAC) circuits arranged to multiply and accumulate data. In a first operational mode the convolutional accelerator stores feature data in the feature line buffer memory and stores kernel data in the kernel data buffer memory. In a second mode of operation, the convolutional accelerator stores kernel decompression tables in the feature line buffer memory.